Intelligent surveying and mapping data management method and system

Abstract

The application provides an intelligent surveying and mapping data management method and system, and relates to the technical field of artificial intelligence.In the application, first data application action information and second data application action information of a to-be-processed surveying and mapping data user are determined; based on the first data application action information and the second data application action information, a first ordered set of application actions and a second ordered set of application actions are determined; based on the first ordered set of application actions and the second ordered set of application actions, a to-be-analyzed feature representation of target stored surveying and mapping data is analyzed; according to the to-be-analyzed feature representation of the target stored surveying and mapping data, an application correlation representation parameter of the to-be-processed surveying and mapping data user for each target stored surveying and mapping data is analyzed; and based on the size order between the application correlation representation parameters, a target data management operation is performed on the target stored surveying and mapping data.Based on the above, the reliability of data management can be improved to a certain extent.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and more specifically, to an intelligent surveying and mapping data management method and system. Background Technology

[0002] Surveying and mapping data includes surveying text data and surveying image data. The management of surveying and mapping data generally involves compression, transmission, and storage. However, current technologies typically manage surveying and mapping data based on information such as the time of collection and random manual allocation, leading to issues of low reliability. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide an intelligent surveying and mapping data management method and system, so as to improve the reliability of data management to a certain extent.

[0004] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0005] A method for intelligent surveying and mapping data management, comprising:

[0006] The system determines the first data application action information of the user of the mapping data to be processed within the target interval of the action, and determines the second data application action information of the user of the mapping data to be processed within the sub-interval of the action. The width of the target interval of the action is greater than the width of the sub-interval of the action. The target interval of the action includes the sub-interval of the action. Both the target interval of the action and the sub-interval of the action belong to a time interval. The first data application action information and the second data application action information are used to reflect the application actions performed by the user of the mapping data to be processed on the stored mapping data. The first data application action information and the second data application action information are text data. The stored mapping data includes text mapping data and / or image mapping data.

[0007] Based on the first data application action information and the second data application action information, a first ordered set of a first number of application actions and a second ordered set of a second number of application actions are determined. The first ordered set of application actions includes application action key information at the same data level within the target interval of the action, and the second ordered set of application actions includes application action key information at each data level within the sub-interval of the action.

[0008] Based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions, the user of the mapping data to be processed is analyzed to obtain the feature representation of the third number of target stored mapping data.

[0009] Based on the user's analysis of the third number of target stored surveying data, the correlation analysis network is used to analyze the application correlation characterization parameters of the user's application of each target stored surveying data.

[0010] The application relevance representation parameters of the target stored surveying data to be processed are sorted by size for each target stored surveying data user, and target data management operations are performed on the third number of target stored surveying data based on the size sorting of the application relevance representation parameters.

[0011] In some preferred embodiments, in the above-described intelligent surveying and mapping data management method, the step of determining a first ordered set of a first number of application actions and a second ordered set of a second number of application actions based on the first data application action information and the second data application action information includes:

[0012] Based on the first data application action information, according to the corresponding data level, a first ordered set of a first number of application actions is analyzed.

[0013] Based on the corresponding data level and the second data application action information, a second ordered set of a second number of application actions is analyzed.

[0014] In some preferred embodiments, in the above-described intelligent mapping data management method, the step of analyzing a first ordered set of a first number of application actions based on the first data application action information according to the corresponding data level includes:

[0015] The first data application action information is used to perform application action mining operation to output the first application action corresponding to each of the first number of data layers within the target interval of the action. The first application action belongs to the action corresponding to the user application operation of the target stored surveying data by the user of the surveying data to be processed.

[0016] Based on the first application actions corresponding to the first number of data layers within the target interval of the action, a first ordered set of the first number of application actions is formed. The first ordered set of application actions includes a first feature representation of the application action. The first feature representation of the application action is formed by performing key data mining on the data of the corresponding data layer of the first application action. One first ordered set of application actions corresponds to one data layer.

[0017] In some preferred embodiments, in the above-described intelligent mapping data management method, the step of analyzing a second ordered set of a second number of application actions based on the second data application action information according to the corresponding data level includes:

[0018] The second data application action information is used to perform application action mining operation to output a second number of second application actions within the action execution sub-interval. The second application action belongs to the action corresponding to the user application operation of the target stored surveying data by the user of the surveying data to be processed.

[0019] Based on the second number of second application actions within the sub-interval of the action, a second ordered set of the second number of application actions is formed. The second ordered set of application actions includes a second feature representation of the application actions. The second feature representation of the application actions is formed by key data mining of the data of the second application actions at each data level. One second ordered set of application actions corresponds to one second application action.

[0020] In some preferred embodiments, in the above-described intelligent surveying and mapping data management method, the step of analyzing the unanalyzed feature representation of the user of the surveying and mapping data to be processed for a third number of target stored surveying and mapping data based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions includes:

[0021] Based on the first ordered set of the first number of application actions, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined;

[0022] Based on the second ordered set of the second number of application actions, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined;

[0023] The first local feature representation and the second local feature representation are aggregated to form the corresponding feature representation to be analyzed.

[0024] In some preferred embodiments, the intelligent surveying and mapping data management method described above further includes:

[0025] The user identity data of the user whose surveying data to be processed is determined;

[0026] The user identity data of the users in the mapping data to be processed is subjected to key data mining operations to form a user identity feature representation of the users in the mapping data to be processed.

[0027] The step of mining the first local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed, based on the first ordered set of the first number of application actions, includes:

[0028] Based on the first ordered set of the first number of application actions and the user identity feature representation of the user of the mapping data to be processed, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed;

[0029] The step of mining the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions includes:

[0030] Based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the mapping data to be processed, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed;

[0031] The step of aggregating the feature representations of the first local feature representation and the second local feature representation to form a corresponding feature representation to be analyzed includes:

[0032] An aggregation operation is performed on the first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed to form a corresponding feature representation to be analyzed.

[0033] In some preferred embodiments, the intelligent surveying and mapping data management method described above further includes:

[0034] The stored mapping data feature representation clusters are mined, and each stored mapping data feature representation cluster includes a fourth number of stored mapping data feature representation sub-clusters. Each stored mapping data feature representation sub-cluster includes stored mapping data feature representations of the same data level of the third number of target stored mapping data. The stored mapping data feature representation sub-clusters are different from each other in that the data level corresponding to the stored mapping data feature representations is different.

[0035] The step of analyzing the first local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the first ordered set of the first number of application actions and the user identity feature representation of the user of the surveying data to be processed includes:

[0036] Based on the first ordered set of the first number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed;

[0037] The step of analyzing the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the surveying data to be processed includes:

[0038] Based on the second ordered set of the second number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed;

[0039] The step of analyzing the application correlation characterization parameters of the user of the mapping data to be processed for each of the third number of target stored mapping data based on the user's analysis feature representation of the mapping data to be processed for a third number of target stored mapping data using a correlation analysis network includes:

[0040] Based on the feature representation to be analyzed and the feature representation cluster of the stored mapping data, the correlation analysis network is used to analyze the application correlation characterization parameters of the user of the mapping data to be processed for each target stored mapping data.

[0041] In some preferred embodiments, in the above-described intelligent surveying and mapping data management method, the steps of sorting the application relevance characterization parameters of the surveying and mapping data users to each target stored surveying and mapping data, and performing target data management operations on the third number of target stored surveying and mapping data based on the sorting of the application relevance characterization parameters, include:

[0042] The application relevance representation parameters of each target stored surveying data are sorted by size, and the third number of target stored surveying data are sorted according to the size sorting result to form a target stored surveying data set. In the target stored surveying data set, the application relevance representation parameter corresponding to the target stored surveying data that is sorted first is greater than or equal to the application relevance representation parameter corresponding to the target stored surveying data that is sorted later.

[0043] The target stored mapping data set is traversed;

[0044] The target stored mapping data currently being traversed is compressed to form compressed target stored mapping data. The compression ratio corresponding to this compression operation has a negative correlation with the corresponding traversal stage. The compression ratio is equal to the ratio of the data volume between the compressed target stored mapping data and the target stored mapping data currently being traversed.

[0045] The compressed target storage mapping data corresponding to each target storage mapping data in the target storage mapping data set is stored.

[0046] In some preferred embodiments, the intelligent surveying and mapping data management method described above further includes:

[0047] The following are identified: an example first application action information cluster, an example second application action information cluster, a target stored mapping data cluster, and an actual correlation characterization parameter cluster for the user of the mapping data to be processed. The example first application action information cluster includes multiple example first application action information clusters, and the example second application action information cluster includes multiple example second application action information clusters. The application action information included in the example first and example second application action information clusters reflects the application actions performed by the user of the mapping data to be processed on the stored mapping data. The application action information included in the example first and example second application action information clusters belongs to different action ranges. The target stored mapping data cluster includes the third number of target stored mapping data. The actual correlation characterization parameter cluster includes the actual correlation characterization parameters corresponding to each target stored mapping data for the user of the mapping data to be processed.

[0048] Based on the example first application action information cluster and the example second application action information cluster, the example action first ordered set cluster and the example action second ordered set cluster are analyzed. The example action first ordered set cluster includes multiple example action first ordered sets, and the example action second ordered set cluster includes multiple example action second ordered sets. The example action first ordered set includes application action key information at the same data level, and the example action second ordered set includes application action key information at each data level.

[0049] Based on the first ordered set cluster of example actions and the second ordered set cluster of example actions, the unanalyzed feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed;

[0050] Based on the user's analysis of the third number of target stored mapping data and the target stored mapping data cluster, the application correlation characterization parameters of the user's application of each target stored mapping data are analyzed using a candidate correlation analysis network.

[0051] Based on the actual correlation characterization parameter cluster and the application correlation characterization parameters of the mapping data user for each target stored mapping data, the candidate correlation analysis network is optimized to form the corresponding correlation analysis network.

[0052] This invention also provides an intelligent surveying and mapping data management system, including a processor and a memory. The memory is used to store computer programs, and the processor is used to execute the computer programs to implement the above-described intelligent surveying and mapping data management method.

[0053] The intelligent surveying and mapping data management method and system provided in this invention can first determine the first data application action information and the second data application action information of the user of the surveying and mapping data to be processed; based on the first data application action information and the second data application action information, determine the first ordered set of application actions and the second ordered set of application actions; based on the first ordered set of application actions and the second ordered set of application actions, analyze the feature representation to be analyzed for the target stored surveying and mapping data; based on the feature representation to be analyzed for the target stored surveying and mapping data, analyze the application relevance characterization parameters of the user of the surveying and mapping data to be processed for each target stored surveying and mapping data; and perform target data management operations on the target stored surveying and mapping data based on the size ranking of the application relevance characterization parameters. Based on the foregoing, since the application action information within intervals of different widths is used to determine the first ordered set and the second ordered set of application actions, and since the first ordered set of application actions includes key information of application actions at the same data level within the target interval of the action, while the second ordered set of application actions includes key information of application actions at each data level within the sub-interval of the action, feature mining can be performed on the first ordered set and the second ordered set of application actions of the user of the surveying and mapping data to be processed. This allows the user of the surveying and mapping data to be processed to obtain the feature representation to be analyzed for multiple target stored surveying and mapping data. This feature representation can accurately characterize the key information of application actions of the user of the surveying and mapping data to be processed at each data level within different intervals. As a result, the application correlation representation parameters of the user of the surveying and mapping data to be processed for multiple target stored surveying and mapping data output by the correlation analysis network are more consistent with the actual situation of the user of the surveying and mapping data to be processed. That is, the accuracy of the application correlation representation parameters of multiple target stored surveying and mapping data is high. Therefore, the reliability of data management can be improved to a certain extent, and the problem of low reliability in the existing technology can be improved.

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0055] Figure 1 This is a structural block diagram of the intelligent surveying and mapping data management system provided in an embodiment of the present invention.

[0056] Figure 2 The flowchart illustrates the steps of the intelligent surveying and mapping data management method provided in this embodiment of the invention.

[0057] Figure 3 This is a schematic diagram of the modules included in the intelligent surveying and mapping data management device provided in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0059] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0060] like Figure 1 As shown, this embodiment of the invention provides an intelligent surveying and mapping data management system. The intelligent surveying and mapping data management system may include a memory and a processor.

[0061] In detail, the memory and the processor are electrically connected directly or indirectly to enable data transmission or interaction. For example, they can be electrically connected via one or more communication buses or signal lines. The memory may store at least one software functional module (computer program) that exists in the form of software or firmware. The processor can be used to execute the executable computer program stored in the memory, thereby implementing the intelligent surveying data management method provided in this embodiment of the invention.

[0062] It should be understood that, in some possible implementations, the memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0063] It should be understood that, in some possible implementations, the processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0064] It should be understood that, in some possible implementations, the intelligent surveying and mapping data management system may be a server with data processing capabilities.

[0065] Combination Figure 2 This invention also provides an intelligent surveying and mapping data management method, which can be applied to the aforementioned intelligent surveying and mapping data management system. The method steps defined in the relevant processes of the intelligent surveying and mapping data management method can be implemented by the intelligent surveying and mapping data management system.

[0066] The following will be about Figure 2 The specific process shown will be explained in detail.

[0067] Step S110: Determine the first data application action information of the user of the mapping data to be processed within the target interval of the action, and determine the second data application action information of the user of the mapping data to be processed within the sub-interval of the action.

[0068] In this embodiment of the invention, the intelligent surveying and mapping data management system can determine the first data application action information of the user of the surveying and mapping data to be processed within the target action interval, and determine the second data application action information of the user of the surveying and mapping data to be processed within the sub-action interval. The width of the target action interval is greater than the width of the sub-action interval, and the target action interval includes the sub-action interval. Both the target action interval and the sub-action interval belong to time intervals. That is, the first data application action information belongs to the data application action information within the most recent larger time interval, and the second data application action information belongs to the data application action information within the most recent smaller time interval. The first and second data application action information are used to reflect the application actions performed by the user of the surveying and mapping data to be processed on the stored surveying and mapping data, such as data modification actions, data reading actions, etc. The first and second data application action information are text data, and the stored surveying and mapping data includes text surveying and mapping data and / or image surveying and mapping data.

[0069] Step S120: Based on the first data application action information and the second data application action information, determine a first ordered set of a first number of application actions and a second ordered set of a second number of application actions.

[0070] In this embodiment of the invention, the intelligent surveying and mapping data management system can determine a first ordered set of a first number of application actions and a second ordered set of a second number of application actions based on the first data application action information and the second data application action information. The first ordered set of application actions includes key information of application actions at the same data level within the target interval of the action, and the second ordered set of application actions includes key information of application actions at each data level within the sub-interval of the action. The data level can refer to the time of the data application action, the object of the data application action, the type of the data application action, the amount of object data of the data application action, the time interval between the previous data application action, etc.

[0071] Step S130: Based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions, analyze the feature representation of the user of the mapping data to be processed for the third number of target stored mapping data.

[0072] In this embodiment of the invention, the intelligent surveying and mapping data management system can analyze the unanalyzed feature representation of the user of the surveying and mapping data to be processed for a third number of target stored surveying and mapping data based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions. The third number of target stored surveying and mapping data can be all stored surveying and mapping data, or a portion of all stored surveying and mapping data.

[0073] Step S140: Based on the analysis feature representation of the third number of target stored surveying data by the user of the surveying data to be processed, the application correlation characterization parameters of the user of the surveying data to be processed for each target stored surveying data are analyzed using a correlation analysis network.

[0074] In this embodiment of the invention, the intelligent surveying and mapping data management system can, based on the unanalyzed feature representations of the surveying and mapping data user for a third number of target stored surveying and mapping data, utilize a correlation analysis network to analyze the application relevance characterization parameter of the surveying and mapping data user for each target stored surveying and mapping data. The application relevance characterization parameter can refer to the probability of the surveying and mapping data user's demand for the target stored surveying and mapping data. For example, the larger the application relevance characterization parameter, the greater the probability that the surveying and mapping data user will have a demand for the target stored surveying and mapping data in the future, i.e., the greater the probability of taking subsequent action.

[0075] Step S150: Sort the application relevance characterization parameters of the user of the mapping data to be processed for each target stored mapping data by size, and perform target data management operation on the third number of target stored mapping data based on the size sorting of the application relevance characterization parameters.

[0076] In this embodiment of the invention, the intelligent surveying and mapping data management system can sort the application relevance parameters of each target stored surveying and mapping data by user, and perform target data management operations on the third number of target stored surveying and mapping data based on the sorting of application relevance parameters. Since the application relevance parameters represent the probability of subsequent actions, performing target data management operations based on these parameters makes the management operations more reliable, thus facilitating the execution of subsequent actions.

[0077] Based on the foregoing (as described in steps S110-S150), since the application action information within intervals of different widths is used to determine the first ordered set and the second ordered set of application actions, and since the first ordered set of application actions includes key information of application actions at the same data level within the target interval of the action, and the second ordered set of application actions includes key information of application actions at each data level within the sub-interval of the action, feature mining can be performed on the first ordered set and the second ordered set of application actions of the user of the mapping data to be processed. This allows the user of the mapping data to be processed to obtain the feature representation to be analyzed for multiple target stored mapping data. This feature representation can accurately characterize the key information of application actions of the user of the mapping data to be processed at each data level within different intervals. As a result, the application correlation representation parameters of the user of the mapping data to be processed for multiple target stored mapping data output by the correlation analysis network are more consistent with the actual situation of the user of the mapping data to be processed. That is, the accuracy of the application correlation representation parameters of multiple target stored mapping data is high. Therefore, the reliability of data management can be improved to a certain extent, thus improving the problem of low reliability in the prior art.

[0078] It should be understood that, in some possible implementations, step S120 above, namely, determining a first ordered set of a first number of application actions and a second ordered set of a second number of application actions based on the first data application action information and the second data application action information, may further include the following specific implementation process:

[0079] Based on the first data application action information according to the corresponding data level, a first number of application actions first ordered sets are analyzed. For each application action first ordered set, the application action first ordered set may include application action key information at the same data level. For example, the first application action first ordered set includes the application action key information of each first data application action at the first data level, the second application action first ordered set includes the application action key information of each first data application action at the second data level, the third application action first ordered set includes the application action key information of each first data application action at the third data level, the fourth application action first ordered set includes the application action key information of each first data application action at the fourth data level, etc.

[0080] Based on the second data application action information according to the corresponding data level, a second number of second ordered sets of application actions are analyzed. For each second ordered set of application actions, the second ordered set of application actions includes key information of application actions at each data level. For example, the first second ordered set of application actions includes key information of the first data application action at each data level, the second second ordered set of application actions includes key information of the second data application action at each data level, and so on.

[0081] It should be understood that, in some possible implementations, the step of analyzing a first ordered set of a first number of application actions based on the first data application action information according to the corresponding data level may further include the following specific implementation process:

[0082] The first data application action information is used to perform application action mining operation to output the first application action corresponding to each of the first number of data layers within the target interval of the action. The first application action belongs to the action corresponding to the user application operation of the target stored surveying data by the user of the surveying data to be processed.

[0083] Based on the first application actions corresponding to a first number of data layers within the target interval of the action, a first ordered set of the first number of application actions is formed. The first ordered set of application actions includes a first feature representation of the application action. The first feature representation of the application action is formed by key data mining of the data at the corresponding data layer of the first application action. One first ordered set of application actions corresponds to one data layer. The first feature representation of the application action included in the first ordered set of application actions is formed by mining the data at the corresponding data layer of a first application action, such as through an encoding network.

[0084] It should be understood that, in some possible implementations, the step of analyzing a second ordered set of a second number of application actions based on the second data application action information according to the corresponding data level may further include the following specific implementation process:

[0085] The second data application action information is used to perform application action mining operation to output a second number of second application actions within the action execution sub-interval. The second application action belongs to the action corresponding to the user application operation of the target stored surveying data (any target stored surveying data) by the user of the surveying data to be processed.

[0086] Based on the second number of second application actions within the sub-interval of the action, a second ordered set of the second number of application actions is formed. The second ordered set of application actions includes a second feature representation of the application action. The second feature representation of the application action is formed by key data mining of the data of the second application action at each data level. One second ordered set of application actions corresponds to one second application action. The second feature representation of each application action included in the second ordered set of application actions is formed by mining the data of each data level of a second application action, such as by using an encoding network.

[0087] It should be understood that, in some possible implementations, step S130 above, namely, the step of analyzing the user's representation of the target mapping data to be analyzed for a third number of target stored mapping data based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions, further includes the following specific implementation process:

[0088] Based on the first ordered set of the first number of application actions, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined, that is, deep feature mining is performed to form the corresponding deep feature representation.

[0089] Based on the second ordered set of the second number of application actions, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined, that is, deep feature mining is performed to form the corresponding deep feature representation;

[0090] The first local feature representation and the second local feature representation are aggregated to form a corresponding feature representation to be analyzed. For example, the first local feature representation and the second local feature representation can be weighted and superimposed to form a feature representation to be analyzed. The corresponding weighting coefficients can be determined by the corresponding neural network during the network optimization process.

[0091] It should be understood that, in some possible implementations, the intelligent surveying and mapping data management method may further include the following specific implementation processes:

[0092] The user identity data of the users whose surveying and mapping data is to be processed is determined (such as the user's occupation, working age, and other data related to the surveying and mapping field); the user identity data of the users whose surveying and mapping data is to be processed is subjected to key data mining operations, for example, through an encoding network, to form a user identity feature representation of the users whose surveying and mapping data is to be processed.

[0093] Based on the above, the step of mining the first local feature representation of the user of the third number of target stored surveying data based on the first ordered set of the first number of application actions can further include the following specific implementation process:

[0094] Based on the first ordered set of the first number of application actions and the user identity feature representation of the user of the mapping data to be processed, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed. That is, the user identity feature representation of the user of the mapping data to be processed is fused in the first ordered set of the first number of application actions.

[0095] Based on the above, the step of mining the second local feature representation of the user of the third number of target stored surveying data based on the second ordered set of the second number of application actions can further include the following specific implementation process:

[0096] Based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the mapping data to be processed, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed. That is, the user identity feature representation of the user of the mapping data to be processed is fused in the second ordered set of the second number of application actions.

[0097] Based on the above, the step of aggregating the first local feature representation and the second local feature representation to form the corresponding feature representation to be analyzed can further include the following specific implementation process:

[0098] An aggregation operation is performed on the first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed to form a corresponding feature representation to be analyzed. That is, the information from the first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed is aggregated.

[0099] It should be understood that, in some possible implementations, the intelligent surveying and mapping data management method may further include the following specific implementation processes:

[0100] The stored mapping data feature representation clusters are mined, each cluster comprising a fourth number of stored mapping data feature representation sub-clusters. Each sub-cluster includes stored mapping data feature representations at the same data level from the third number of target stored mapping data (e.g., feature mining can be performed on the target stored mapping data to form stored mapping data feature representations). The data levels corresponding to the stored mapping data feature representations differ between the sub-clusters. The third number is greater than or equal to the first number, meaning that the data levels of the target stored mapping data are more than or equal to the data levels of the first data application action information. In some applications, they can be equal.

[0101] Based on the above, the step of analyzing the first local feature representation of the third number of target stored surveying data by the user of the first ordered set of the first number of application actions and the user identity feature representation of the user of the surveying data to be processed can further include the following specific implementation process:

[0102] Based on the first ordered set of the first number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed. In other words, the information from the third aspect can be fused to form the first local feature representation.

[0103] It should be understood that, in some possible implementations, the step of analyzing the first local feature representation of the user of the surveying and mapping data to be processed for the third number of target stored surveying and mapping data based on the first ordered set of the first number of application actions, the user identity feature representation of the user of the surveying and mapping data to be processed, and the feature representation cluster of the stored surveying and mapping data may further include the following specific implementation process:

[0104] For each of the first ordered sets of application actions in the first ordered set of the first number of application actions, in the stored mapping data feature representation cluster, the stored mapping data feature representation sub-cluster corresponding to the data layer of the first ordered set of application actions is determined, and the stored mapping data feature representations included in the stored mapping data feature representation sub-cluster are concatenated and combined to form a corresponding stored concatenated and combined feature representation. Then, the dot product between the stored concatenated and combined feature representation and the user identity feature representation of the user of the mapping data to be processed is calculated, and the dot product is normalized to form the fusion coefficient corresponding to the first ordered set of application actions. When performing the normalization operation, the dot product corresponding to a data layer can be divided by the sum of the dot products of each data layer to obtain the corresponding fusion coefficient.

[0105] For each of the first ordered sets of application actions in the first ordered set of the first number of application actions, a concatenation combination operation is performed on the first feature representations of each application action included in the first ordered set of application actions to form a first concatenation combination feature representation corresponding to the first ordered set of application actions. In addition, based on the fusion coefficient (as a weighting coefficient) corresponding to each first ordered set of application actions, a weighted superposition operation is performed on the first concatenation combination feature representation corresponding to each first ordered set of application actions to form a first local feature representation of the mapping data user to be processed for the third number of target stored mapping data. Alternatively, a further linear mapping operation can be performed on the result of the weighted superposition operation to obtain the first local feature representation.

[0106] Based on the above, the step of analyzing the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the surveying data to be processed can further include the following specific implementation process:

[0107] Based on the second ordered set of the second number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed. In other words, the information from the third aspect can be fused to form the second local feature representation.

[0108] It should be understood that, in some possible implementations, the step of analyzing the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions, the user identity feature representation of the user of the surveying data to be processed, and the feature representation cluster of the stored surveying data may further include the following specific implementation process:

[0109] For one of the second ordered sets of application actions (the same processing can be performed on each second ordered set of application actions sequentially or simultaneously), a target computation operation is performed on the second ordered set of application actions to output the feature representation and importance representation parameters corresponding to the second ordered set of application actions.

[0110] Based on the importance representation parameters (as weighting coefficients) corresponding to the second ordered set of each application action, a weighted superposition operation is performed on the feature representation to be processed corresponding to the second ordered set of each application action to output the second local feature representation of the mapping data user to the third number of target stored mapping data.

[0111] It should be understood that, in some possible implementations, the step of performing a target computation operation on one of the second ordered sets of application actions from the second number of second ordered sets of application actions to output the feature representation and importance representation parameters corresponding to the second ordered set of application actions may include:

[0112] For the first calculation stage, the second feature representations of the application actions included in the second ordered set of application actions are concatenated and combined to form a second concatenated combined feature representation corresponding to the second ordered set of application actions. Additionally, the stored mapping data feature representations included in the stored mapping data feature representation cluster are concatenated and combined to form a concatenated combined stored data feature representation. Furthermore, a first weighted superposition operation is performed on the second concatenated combined feature representation and the concatenated combined stored data feature representation, and a first shift operation (such as adding a shift parameter) is performed on the result of the weighted superposition operation. Finally, an activation operation is performed on the result of the shift operation to output the calculation stage. The calculation process involves several steps: first, weighted summation of the second concatenated feature representation and the concatenated stored data feature representation; second, shifting the result of the weighted summation (e.g., adding a shift parameter); activation of the shift operation result to output the second indicator parameter corresponding to this calculation stage; and third, weighted summation of the second concatenated feature representation and the concatenated stored data feature representation; third, shifting the result of the weighted summation (e.g., adding a shift parameter); activation of the shift operation result to output the third indicator parameter corresponding to this calculation stage. Furthermore, a fourth weighted superposition operation is performed on the second cascaded combined feature representation and the cascaded combined stored data feature representation, and a fourth shift operation (such as adding a shift parameter) is performed on the result of the weighted superposition operation. Then, an activation operation is performed on the result of the shift operation. The first index parameter and the result of the activation operation are multiplied to obtain a first multiplication result. The second index parameter and the user identity feature representation of the user of the mapping data to be processed are multiplied to obtain a second multiplication result. The first and second multiplication results are then superimposed to output the fourth index parameter corresponding to this calculation stage. An activation operation is performed on the fourth index parameter, and the fourth index parameter is then... The three index parameters and the result of the activation operation are multiplied to output the fifth index parameter corresponding to the calculation stage. The dot product between the cascaded combined storage data feature representation and the fifth index parameter is calculated to obtain the sixth index parameter corresponding to the calculation stage. The weighting coefficients of the first weighted superposition operation, the shift parameters of the first shift operation, the weighting coefficients of the second weighted superposition operation, the shift parameters of the second shift operation, the weighting coefficients of the third weighted superposition operation, the shift parameters of the third shift operation, the weighting coefficients of the fourth weighted superposition operation, the shift parameters of the fourth shift operation, and the parameters of the activation operation can all be formed in the network optimization process of the corresponding neural network.

[0113] For each calculation stage following the first calculation stage, a first weighted superposition operation is performed on the fifth index parameter corresponding to the previous calculation stage and the cascaded combined storage data feature representation. The result of the weighted superposition operation is then subjected to a first shift operation (e.g., adding a shift parameter), and the result of the shift operation is activated to output the first index parameter corresponding to that calculation stage. Similarly, a second weighted superposition operation is performed on the fifth index parameter corresponding to the previous calculation stage and the cascaded combined storage data feature representation. The result of the weighted superposition operation is then subjected to a second shift operation (e.g., adding a shift parameter), and the result of the shift operation is activated to output the second index parameter corresponding to that calculation stage. Finally, a third weighted superposition operation is performed on the fifth index parameter corresponding to the previous calculation stage and the cascaded combined storage data feature representation. The result of the weighted superposition operation is then subjected to a third shift operation (e.g., adding a shift parameter), and the result of the shift operation is activated to output the third index parameter corresponding to that calculation stage. The fifth indicator parameter corresponding to the calculation stage and the cascaded combined storage data feature representation are subjected to a fourth weighted superposition operation. The result of the weighted superposition operation is then subjected to a fourth shift operation (such as adding a shift parameter). The result of the shift operation is then subjected to an activation operation. The first indicator parameter of the calculation stage and the result of the activation operation are then multiplied to obtain a first multiplication result. The second indicator parameter of the calculation stage and the fourth indicator parameter of the previous calculation stage are then multiplied to obtain a second multiplication result. The first multiplication result and the second multiplication result are then superimposed to output the fourth indicator parameter corresponding to the calculation stage. The fourth indicator parameter is then activated. The third indicator parameter and the result of the activation operation are then multiplied to output the fifth indicator parameter corresponding to the calculation stage. The dot product between the cascaded combined storage data feature representation and the fifth indicator parameter is calculated. Based on the dot product corresponding to the current calculation stage and each previous calculation stage, the dot product corresponding to the current calculation stage is normalized to obtain the sixth indicator parameter corresponding to the current calculation stage.

[0114] The fifth index parameter calculated in the last calculation stage is used as the feature representation to be processed corresponding to the second ordered set of application actions, and the sixth index parameter calculated in the last calculation stage is used as the importance representation parameter corresponding to the second ordered set of application actions.

[0115] It should be understood that, in some possible implementations, the step of aggregating the feature representations of the first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed to form the corresponding feature representation to be analyzed may further include the following specific implementation process:

[0116] The first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed are weighted and superimposed to form a corresponding weighted superimposed feature representation. The weighting coefficients can be formed in the corresponding network optimization process.

[0117] An activation operation is performed on the weighted superposition feature representation to form the corresponding activation output parameters;

[0118] The first weighting coefficient and the second weighting coefficient are determined based on the activation output parameters, respectively;

[0119] Based on the first weighting coefficient and the second weighting coefficient, the first local feature representation and the second local feature representation are weighted and superimposed to form a corresponding feature representation to be analyzed. The first weighting coefficient corresponding to the first local feature representation has a negative correlation with the activation output parameter, and the second weighting coefficient corresponding to the second local feature representation has a positive correlation with the activation output parameter.

[0120] It should be understood that, in some possible implementations, the step of mining the feature representation clusters of stored mapping data may further include the following specific implementation process:

[0121] The target stored mapping data cluster is extracted, the target stored mapping data cluster includes the third number of target stored mapping data, and the third number of target stored mapping data includes the fourth number of key mapping data at the data level;

[0122] Based on the fourth number of data layers, key data mining operations are performed on the third number of target stored mapping data to output the stored mapping data feature representation subclusters corresponding to each data layer;

[0123] Based on each of the stored mapping data feature representation subclusters corresponding to the data layer, a corresponding stored mapping data feature representation cluster is constructed.

[0124] It should be understood that, in some possible implementations, step S140 above, namely, the step of analyzing the application correlation characterization parameters of the user of the data to be processed for each of the third number of target stored mapping data based on the user's analysis feature representation of the mapping data to be processed for the third number of target stored mapping data using a correlation analysis network, may further include the following specific implementation process:

[0125] Based on the feature representation to be analyzed and the cluster of stored mapping data feature representations, the correlation analysis network is used to analyze the application relevance representation parameters of the user of the mapping data to be processed for each target stored mapping data. For example, the stored mapping data feature representations included in the cluster of stored mapping data feature representations can be classified and combined according to the corresponding target stored mapping data to form a combined feature representation corresponding to each target stored mapping data. Then, the distance between the feature representation to be analyzed and each combined feature representation, such as cosine distance, is calculated. Based on this distance, the application relevance representation parameter of the user of the mapping data to be processed for each target stored mapping data is determined. This application relevance representation parameter can be negatively correlated with the distance.

[0126] It should be understood that, in some possible implementations, step S150 above, namely, sorting the application relevance characterization parameters of the mapping data user for each target stored mapping data, and performing target data management operations on the third number of target stored mapping data based on the sorting of the application relevance characterization parameters, may further include the following specific implementation process:

[0127] The application relevance representation parameters of each target stored surveying data are sorted by size, and the third number of target stored surveying data are sorted according to the size sorting result to form a target stored surveying data set. In the target stored surveying data set, the application relevance representation parameter corresponding to the target stored surveying data that is sorted first is greater than or equal to the application relevance representation parameter corresponding to the target stored surveying data that is sorted later.

[0128] The target stored mapping data set is traversed;

[0129] The target stored mapping data that is currently being traversed is compressed to form compressed target stored mapping data. The compression ratio corresponding to this compression operation has a negative correlation with the corresponding traversal stage. The compression ratio is equal to the ratio of the data volume between the compressed target stored mapping data and the target stored mapping data that is currently being traversed. That is, the larger the corresponding application relevance characterization parameter, the larger the compression ratio of the compressed target stored mapping data.

[0130] The compressed target storage mapping data corresponding to each target storage mapping data in the target storage mapping data set is stored.

[0131] It should be understood that, in some possible implementations, the intelligent surveying and mapping data management method may further include the following specific implementation processes:

[0132] The following are identified: an example first application action information cluster, an example second application action information cluster, a target stored mapping data cluster, and an actual correlation characterization parameter cluster for the user of the mapping data to be processed. The example first application action information cluster includes multiple example first application action information clusters, and the example second application action information cluster includes multiple example second application action information clusters. The application action information included in the example first and example second application action information clusters reflects the application actions performed by the user of the mapping data to be processed on the stored mapping data. The application action information included in the example first and example second application action information clusters belongs to different action intervals. The target stored mapping data cluster includes the third number of target stored mapping data. The actual correlation characterization parameter cluster includes the actual correlation characterization parameters corresponding to each target stored mapping data by the user of the mapping data to be processed. The intervals corresponding to the example first and example second application action information clusters are earlier than the target interval.

[0133] Based on the first example application action information cluster and the second example application action information cluster, the first example action ordered set cluster and the second example action ordered set cluster are analyzed. The first example action ordered set cluster includes multiple first example action ordered sets, and the second example action ordered set cluster includes multiple second example action ordered sets. The first example action ordered set includes application action key information at the same data level, and the second example action ordered set includes application action key information at different data levels, as described above.

[0134] Based on the first ordered set cluster of example actions and the second ordered set cluster of example actions, the user of the mapping data to be processed is analyzed to obtain the unanalyzed feature representation of the third number of target stored mapping data, as described above.

[0135] Based on the user's analysis of the third number of target stored surveying data and the target stored surveying data cluster, the application correlation characterization parameters of the user's application of each target stored surveying data are analyzed using a candidate correlation analysis network, as described above.

[0136] Based on the actual correlation characterization parameter cluster and the application correlation characterization parameters of the mapping data user for each target stored mapping data, the candidate correlation analysis network is optimized to form a corresponding correlation analysis network. For example, the network optimization cost index can be calculated first based on the difference between the actual correlation characterization parameter cluster and the application correlation characterization parameters of the mapping data user for each target stored mapping data. Based on the network optimization cost index, the network parameters of the candidate correlation analysis network are optimized and adjusted to form a corresponding correlation analysis network. During the optimization and adjustment process, the optimization is carried out in the direction of reducing the network optimization cost index.

[0137] Combination Figure 3 This invention also provides an intelligent surveying and mapping data management device, which can be applied to the aforementioned intelligent surveying and mapping data management system. The intelligent surveying and mapping data management device may include:

[0138] The action information determination module is used to determine the first data application action information of the user of the mapping data to be processed within the action execution target interval, and to determine the second data application action information of the user of the mapping data to be processed within the action execution sub-interval. The interval width of the action execution target interval is greater than the interval width of the action execution sub-interval. The action execution target interval includes the action execution sub-interval. Both the action execution target interval and the action execution sub-interval belong to a time interval. The first data application action information and the second data application action information are used to reflect the application actions performed by the user of the mapping data to be processed on the stored mapping data. The first data application action information and the second data application action information are text data. The stored mapping data includes text mapping data and / or image mapping data.

[0139] The action ordered set determination module is used to determine a first number of first ordered sets of application actions and a second number of second ordered sets of application actions based on the first data application action information and the second data application action information. The first ordered set of application actions includes application action key information at the same data level within the target interval of the action, and the second ordered set of application actions includes application action key information at each data level within the sub-interval of the action.

[0140] The feature representation analysis module is used to analyze the feature representation of the user of the mapping data to be processed on the third number of target stored mapping data based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions.

[0141] The application correlation analysis module is used to analyze the application correlation characterization parameters of the user of the mapping data to be processed for each of the third number of target stored mapping data based on the analysis feature representation of the mapping data user to be processed for the third number of target stored mapping data using a correlation analysis network.

[0142] The target data management module is used to sort the application relevance characterization parameters of each target stored surveying data by user, and to perform target data management operations on the third number of target stored surveying data based on the sorting of application relevance characterization parameters.

[0143] In summary, the intelligent surveying and mapping data management method and system provided by this invention can first determine the first data application action information and the second data application action information of the user of the surveying and mapping data to be processed; based on the first data application action information and the second data application action information, determine the first ordered set of application actions and the second ordered set of application actions; based on the first ordered set of application actions and the second ordered set of application actions, analyze the feature representation to be analyzed for the target stored surveying and mapping data; based on the feature representation to be analyzed for the target stored surveying and mapping data, analyze the application relevance characterization parameters of the user of the surveying and mapping data to be processed for each target stored surveying and mapping data; and perform target data management operations on the target stored surveying and mapping data based on the size ranking of the application relevance characterization parameters. Based on the foregoing, since the application action information within intervals of different widths is used to determine the first ordered set and the second ordered set of application actions, and since the first ordered set of application actions includes key information of application actions at the same data level within the target interval of the action, while the second ordered set of application actions includes key information of application actions at each data level within the sub-interval of the action, feature mining can be performed on the first ordered set and the second ordered set of application actions of the user of the surveying and mapping data to be processed. This allows the user of the surveying and mapping data to be processed to obtain the feature representation to be analyzed for multiple target stored surveying and mapping data. This feature representation can accurately characterize the key information of application actions of the user of the surveying and mapping data to be processed at each data level within different intervals. As a result, the application correlation representation parameters of the user of the surveying and mapping data to be processed for multiple target stored surveying and mapping data output by the correlation analysis network are more consistent with the actual situation of the user of the surveying and mapping data to be processed. That is, the accuracy of the application correlation representation parameters of multiple target stored surveying and mapping data is high. Therefore, the reliability of data management can be improved to a certain extent, and the problem of low reliability in the existing technology can be improved.

[0144] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent surveying and mapping data management, characterized in that, include: The system determines the first data application action information of the user of the mapping data to be processed within the target interval of the action, and determines the second data application action information of the user of the mapping data to be processed within the sub-interval of the action. The width of the target interval of the action is greater than the width of the sub-interval of the action. The target interval of the action includes the sub-interval of the action. Both the target interval of the action and the sub-interval of the action belong to a time interval. The first data application action information and the second data application action information are used to reflect the application actions performed by the user of the mapping data to be processed on the stored mapping data. The first data application action information and the second data application action information are text data. The stored mapping data includes text mapping data and / or image mapping data. Based on the first data application action information and the second data application action information, a first ordered set of a first number of application actions and a second ordered set of a second number of application actions are determined. The first ordered set of application actions includes application action key information at the same data level within the target interval of the action, and the second ordered set of application actions includes application action key information at each data level within the sub-interval of the action. Based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions, the user of the mapping data to be processed is analyzed to obtain the feature representation of the third number of target stored mapping data. Based on the user's analysis of the third number of target stored surveying data, the correlation analysis network is used to analyze the application correlation characterization parameters of the user's application of each target stored surveying data. The application relevance characterization parameters of the user to be processed for each target stored surveying data are sorted by size, and target data management operations are performed on the third number of target stored surveying data based on the size sorting of the application relevance characterization parameters. The step of analyzing the user's representation of the target stored mapping data for a third number of purposes based on the first ordered set of the first number of application actions and the second ordered set of the second number of application actions includes: Based on the first ordered set of the first number of application actions, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined; Based on the second ordered set of the second number of application actions, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is mined; The first local feature representation and the second local feature representation are aggregated to form the corresponding feature representation to be analyzed; The intelligent surveying and mapping data management method also includes: The user identity data of the user whose surveying data to be processed is determined; The user identity data of the users in the mapping data to be processed is subjected to key data mining operations to form a user identity feature representation of the users in the mapping data to be processed. The step of mining the first local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed, based on the first ordered set of the first number of application actions, includes: Based on the first ordered set of the first number of application actions and the user identity feature representation of the user of the mapping data to be processed, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed; The step of mining the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions includes: Based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the mapping data to be processed, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed; The step of aggregating the feature representations of the first local feature representation and the second local feature representation to form a corresponding feature representation to be analyzed includes: An aggregation operation is performed on the first local feature representation, the second local feature representation, and the user identity feature representation of the user of the mapping data to be processed to form a corresponding feature representation to be analyzed; The intelligent surveying and mapping data management method also includes: The stored mapping data feature representation clusters are mined, and each stored mapping data feature representation cluster includes a fourth number of stored mapping data feature representation sub-clusters. Each stored mapping data feature representation sub-cluster includes stored mapping data feature representations of the same data level of the third number of target stored mapping data. The stored mapping data feature representation sub-clusters are different from each other in that the data level corresponding to the stored mapping data feature representations is different. The step of analyzing the first local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the first ordered set of the first number of application actions and the user identity feature representation of the user of the surveying data to be processed includes: Based on the first ordered set of the first number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the first local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed; The step of analyzing the second local feature representation of the third number of target stored surveying data by the user of the surveying data to be processed based on the second ordered set of the second number of application actions and the user identity feature representation of the user of the surveying data to be processed includes: Based on the second ordered set of the second number of application actions, the user identity feature representation of the user of the mapping data to be processed, and the feature representation cluster of the stored mapping data, the second local feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed; The step of analyzing the application correlation characterization parameters of the user of the mapping data to be processed for each of the third number of target stored mapping data based on the user's analysis feature representation of the mapping data to be processed for a third number of target stored mapping data using a correlation analysis network includes: Based on the feature representation to be analyzed and the feature representation cluster of the stored mapping data, the correlation analysis network is used to analyze the application correlation characterization parameters of the user of the mapping data to be processed for each target stored mapping data.

2. The intelligent surveying and mapping data management method as described in claim 1, characterized in that, The step of determining a first ordered set of a first number of application actions and a second ordered set of a second number of application actions based on the first data application action information and the second data application action information includes: Based on the first data application action information, according to the corresponding data level, a first ordered set of a first number of application actions is analyzed. Based on the corresponding data level and the second data application action information, a second ordered set of a second number of application actions is analyzed.

3. The intelligent surveying and mapping data management method as described in claim 2, characterized in that, The step of analyzing a first ordered set of a first number of application actions based on the first data application action information according to the corresponding data level includes: The first data application action information is used to perform application action mining operation to output the first application action corresponding to each of the first number of data layers within the target interval of the action. The first application action belongs to the action corresponding to the user application operation of the target stored surveying data by the user of the surveying data to be processed. Based on the first application actions corresponding to the first number of data layers within the target interval of the action, a first ordered set of the first number of application actions is formed. The first ordered set of application actions includes a first feature representation of the application action. The first feature representation of the application action is formed by performing key data mining on the data of the corresponding data layer of the first application action. One first ordered set of application actions corresponds to one data layer.

4. The intelligent surveying and mapping data management method as described in claim 2, characterized in that, The step of analyzing a second ordered set of a second number of application actions based on the second data application action information according to the corresponding data level includes: The second data application action information is used to perform application action mining operation to output a second number of second application actions within the action execution sub-interval. The second application action belongs to the action corresponding to the user application operation of the target stored surveying data by the user of the surveying data to be processed. Based on the second number of second application actions within the sub-interval of the action, a second ordered set of the second number of application actions is formed. The second ordered set of application actions includes a second feature representation of the application actions. The second feature representation of the application actions is formed by key data mining of the data of the second application actions at each data level. One second ordered set of application actions corresponds to one second application action.

5. The intelligent surveying and mapping data management method as described in claim 1, characterized in that, The steps of sorting the application relevance parameters of the mapping data to be processed by the user for each target stored mapping data, and performing target data management operations on the third number of target stored mapping data based on the sorting of application relevance parameters, include: The application relevance representation parameters of each target stored surveying data are sorted by size, and the third number of target stored surveying data are sorted according to the size sorting result to form a target stored surveying data set. In the target stored surveying data set, the application relevance representation parameter corresponding to the target stored surveying data that is sorted first is greater than or equal to the application relevance representation parameter corresponding to the target stored surveying data that is sorted later. The target stored mapping data set is traversed; The target stored mapping data currently being traversed is compressed to form compressed target stored mapping data. The compression ratio corresponding to this compression operation has a negative correlation with the corresponding traversal stage. The compression ratio is equal to the ratio of the data volume between the compressed target stored mapping data and the target stored mapping data currently being traversed. The compressed target storage mapping data corresponding to each target storage mapping data in the target storage mapping data set is stored.

6. The intelligent surveying and mapping data management method as described in any one of claims 1-5, characterized in that, The intelligent surveying and mapping data management method also includes: The following are identified: an example first application action information cluster, an example second application action information cluster, a target stored mapping data cluster, and an actual correlation characterization parameter cluster for the user of the mapping data to be processed. The example first application action information cluster includes multiple example first application action information clusters, and the example second application action information cluster includes multiple example second application action information clusters. The application action information included in the example first and example second application action information clusters reflects the application actions performed by the user of the mapping data to be processed on the stored mapping data. The application action information included in the example first and example second application action information clusters belongs to different action ranges. The target stored mapping data cluster includes the third number of target stored mapping data. The actual correlation characterization parameter cluster includes the actual correlation characterization parameters corresponding to each target stored mapping data for the user of the mapping data to be processed. Based on the example first application action information cluster and the example second application action information cluster, the example action first ordered set cluster and the example action second ordered set cluster are analyzed. The example action first ordered set cluster includes multiple example action first ordered sets, and the example action second ordered set cluster includes multiple example action second ordered sets. The example action first ordered set includes application action key information at the same data level, and the example action second ordered set includes application action key information at each data level. Based on the first ordered set cluster of example actions and the second ordered set cluster of example actions, the unanalyzed feature representation of the user of the mapping data to be processed for the third number of target stored mapping data is analyzed; Based on the user's analysis of the third number of target stored mapping data and the target stored mapping data cluster, the application correlation characterization parameters of the user's application of each target stored mapping data are analyzed using a candidate correlation analysis network. Based on the actual correlation characterization parameter cluster and the application correlation characterization parameters of the mapping data user for each target stored mapping data, the candidate correlation analysis network is optimized to form the corresponding correlation analysis network.

7. An intelligent surveying and mapping data management system, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, and the processor being used to execute the computer program to implement the intelligent surveying and mapping data management method according to any one of claims 1-6.

Images